{"id":"https://openalex.org/W2974310638","doi":"https://doi.org/10.1021/acs.jcim.9b00537","title":"Development and Application of a Data-Driven Reaction Classification Model: Comparison of an Electronic Lab Notebook and Medicinal Chemistry Literature","display_name":"Development and Application of a Data-Driven Reaction Classification Model: Comparison of an Electronic Lab Notebook and Medicinal Chemistry Literature","publication_year":2019,"publication_date":"2019-09-17","ids":{"openalex":"https://openalex.org/W2974310638","doi":"https://doi.org/10.1021/acs.jcim.9b00537","mag":"2974310638","pmid":"https://pubmed.ncbi.nlm.nih.gov/31529948"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.9b00537","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.9b00537","pdf_url":"https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.9b00537","source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.9b00537","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008861930","display_name":"Gian Marco Ghiandoni","orcid":"https://orcid.org/0000-0002-2592-2939"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Gian Marco Ghiandoni","raw_affiliation_strings":["Information School, University of Sheffield, Regent Court, 211 Portobello, Sheffield S1\u202f4DP, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information School, University of Sheffield, Regent Court, 211 Portobello, Sheffield S1\u202f4DP, United Kingdom","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103188516","display_name":"Michael J. Bodkin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148098","display_name":"Evotec (United Kingdom)","ror":"https://ror.org/04qvy9k41","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210130816","https://openalex.org/I4210148098"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Michael J. Bodkin","raw_affiliation_strings":["Evotec (U.K.) Ltd., 114 Innovation Drive, Milton Park, Abingdon OX14\u202f4RZ, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Evotec (U.K.) Ltd., 114 Innovation Drive, Milton Park, Abingdon OX14\u202f4RZ, United Kingdom","institution_ids":["https://openalex.org/I4210148098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020099630","display_name":"Beining Chen","orcid":"https://orcid.org/0000-0003-4771-218X"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Beining Chen","raw_affiliation_strings":["Chemistry Department, University of Sheffield, Dainton Building, Brook Hill, Sheffield S3\u202f7HF, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chemistry Department, University of Sheffield, Dainton Building, Brook Hill, Sheffield S3\u202f7HF, United Kingdom","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044955979","display_name":"Dimitar Hristozov","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148098","display_name":"Evotec (United Kingdom)","ror":"https://ror.org/04qvy9k41","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210130816","https://openalex.org/I4210148098"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dimitar Hristozov","raw_affiliation_strings":["Evotec (U.K.) Ltd., 114 Innovation Drive, Milton Park, Abingdon OX14\u202f4RZ, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Evotec (U.K.) Ltd., 114 Innovation Drive, Milton Park, Abingdon OX14\u202f4RZ, United Kingdom","institution_ids":["https://openalex.org/I4210148098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020992924","display_name":"James E. A. Wallace","orcid":"https://orcid.org/0000-0001-7681-2791"},"institutions":[{"id":"https://openalex.org/I4210148098","display_name":"Evotec (United Kingdom)","ror":"https://ror.org/04qvy9k41","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210130816","https://openalex.org/I4210148098"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"James E. A. Wallace","raw_affiliation_strings":["Evotec (U.K.) Ltd., 114 Innovation Drive, Milton Park, Abingdon OX14\u202f4RZ, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Evotec (U.K.) Ltd., 114 Innovation Drive, Milton Park, Abingdon OX14\u202f4RZ, United Kingdom","institution_ids":["https://openalex.org/I4210148098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002436448","display_name":"James Webster","orcid":"https://orcid.org/0000-0002-7014-6350"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"James Webster","raw_affiliation_strings":["Information School, University of Sheffield, Regent Court, 211 Portobello, Sheffield S1\u202f4DP, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information School, University of Sheffield, Regent Court, 211 Portobello, Sheffield S1\u202f4DP, United Kingdom","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030046388","display_name":"Valerie J. Gillet","orcid":"https://orcid.org/0000-0002-8403-3111"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Valerie J. Gillet","raw_affiliation_strings":["Information School, University of Sheffield, Regent Court, 211 Portobello, Sheffield S1\u202f4DP, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-8403-3111","affiliations":[{"raw_affiliation_string":"Information School, University of Sheffield, Regent Court, 211 Portobello, Sheffield S1\u202f4DP, United Kingdom","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5030046388"],"corresponding_institution_ids":["https://openalex.org/I91136226"],"apc_list":null,"apc_paid":null,"fwci":6.0645,"has_fulltext":true,"cited_by_count":52,"citation_normalized_percentile":{"value":0.96733817,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"59","issue":"10","first_page":"4167","last_page":"4187"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10908","display_name":"Analytical Chemistry and Chromatography","score":0.982699990272522,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6713904142379761},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6346622705459595},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43333572149276733},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43134158849716187},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41488566994667053}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6713904142379761},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6346622705459595},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43333572149276733},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43134158849716187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41488566994667053}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D002626","descriptor_name":"Chemistry, Pharmaceutical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D002626","descriptor_name":"Chemistry, Pharmaceutical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D002626","descriptor_name":"Chemistry, Pharmaceutical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D062126","descriptor_name":"Databases, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D062126","descriptor_name":"Databases, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D062126","descriptor_name":"Databases, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1021/acs.jcim.9b00537","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.9b00537","pdf_url":"https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.9b00537","source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:31529948","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31529948","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of chemical information and modeling","raw_type":null},{"id":"pmh:oai:eprints.whiterose.ac.uk:151385","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:discovery.dundee.ac.uk:publications/fa264536-ee78-482f-a1f4-ed57787644db","is_oa":true,"landing_page_url":"https://discovery.dundee.ac.uk/en/publications/fa264536-ee78-482f-a1f4-ed57787644db","pdf_url":"https://discovery.dundee.ac.uk/ws/files/114243472/ghiandoni-et-al-2019-development-and-application-of-a-data-driven-reaction-classification-model-comparison-of-an.pdf","source":{"id":"https://openalex.org/S4306400523","display_name":"Discovery Research Portal (University of Dundee)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177639307","host_organization_name":"University of Dundee","host_organization_lineage":["https://openalex.org/I177639307"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Ghiandoni, G M, Bodkin, M J, Chen, B, Hristozov, D, Wallace, J E A, Webster, J & Gillet, V J 2019, 'Development and Application of a Data-Driven Reaction Classification Model : Comparison of an ELN and the Medicinal Chemistry Literature', Journal of Chemical Information and Modeling, vol. 59, no. 10, pp. 4167-4187. https://doi.org/10.1021/acs.jcim.9b00537","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1021/acs.jcim.9b00537","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.9b00537","pdf_url":"https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.9b00537","source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5500089392","display_name":null,"funder_award_id":"1960252","funder_id":"https://openalex.org/F4320334629","funder_display_name":"Biotechnology and Biological Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F4320334629","display_name":"Biotechnology and Biological Sciences Research Council","ror":"https://ror.org/00cwqg982"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2974310638.pdf"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1969487950","https://openalex.org/W1999241626","https://openalex.org/W2002727413","https://openalex.org/W2008420299","https://openalex.org/W2011006316","https://openalex.org/W2021748110","https://openalex.org/W2040103915","https://openalex.org/W2056701057","https://openalex.org/W2060586571","https://openalex.org/W2070484508","https://openalex.org/W2126363023","https://openalex.org/W2247581895","https://openalex.org/W2277855841","https://openalex.org/W2325811289","https://openalex.org/W2345751939","https://openalex.org/W2606363443","https://openalex.org/W2610135490","https://openalex.org/W2763482850","https://openalex.org/W2769423117","https://openalex.org/W2791657723","https://openalex.org/W2799620402","https://openalex.org/W2888349794","https://openalex.org/W2903262661","https://openalex.org/W2907657781","https://openalex.org/W2910734083","https://openalex.org/W2929387033","https://openalex.org/W3125937743"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"Reaction":[0],"classification":[1,47,88],"has":[2,14],"often":[3],"been":[4,16],"considered":[5],"an":[6,169],"important":[7],"task":[8],"for":[9,70],"many":[10],"different":[11,189],"applications,":[12],"and":[13,40,172,185,206],"traditionally":[15],"accomplished":[17],"using":[18],"hand-coded":[19],"rule-based":[20],"approaches.":[21],"However,":[22],"the":[23,38,76,105,108,131,135,150,156,173,176,201],"availability":[24],"of":[25,28,42,78,107,134,139,149,155,191,203],"large":[26],"collections":[27,205],"reactions":[29],"enables":[30],"data-driven":[31,68],"approaches":[32],"to":[33,56,74,119,126,196],"be":[34,113,127,194],"developed.":[35],"We":[36,64,102,180],"present":[37],"development":[39],"validation":[41,133],"a":[43,51,67,85],"336-class":[44],"machine":[45],"learning-based":[46],"model":[48,111,136,157],"integrated":[49],"within":[50],"Conformal":[52],"Prediction":[53],"(CP)":[54],"framework":[55],"associate":[57],"reaction":[58,72,79,87,163,204,210],"class":[59,186],"predictions":[60,121,140],"with":[61],"confidence":[62,117,183],"estimations.":[63],"also":[65],"propose":[66],"approach":[69],"\"dynamic\"":[71],"fingerprinting":[73],"maximize":[75],"effectiveness":[77],"encoding,":[80],"as":[81,83,141],"well":[82],"developing":[84],"novel":[86],"system":[89],"that":[90,104,122],"organizes":[91],"labels":[92],"into":[93],"four":[94],"hierarchical":[95],"levels":[96,190],"(SHREC:":[97],"Sheffield":[98],"Hierarchical":[99],"REaction":[100],"Classification).":[101],"show":[103,181],"performance":[106],"CP":[109],"augmented":[110],"can":[112,193],"improved":[114],"by":[115,143,160],"defining":[116],"thresholds":[118],"detect":[120],"are":[123],"less":[124,146],"likely":[125],"false.":[128],"For":[129],"example,":[130],"external":[132],"reports":[137],"95%":[138],"correct":[142],"filtering":[144],"out":[145],"than":[147],"15%":[148],"uncertain":[151],"classifications.":[152],"The":[153],"application":[154],"is":[158],"demonstrated":[159],"classifying":[161],"two":[162],"data":[164],"sets:":[165],"one":[166],"extracted":[167],"from":[168,175],"industrial":[170],"ELN":[171],"other":[174],"medicinal":[177],"chemistry":[178],"literature.":[179],"how":[182],"estimations":[184],"compositions":[187],"across":[188],"information":[192],"used":[195],"gain":[197],"immediate":[198],"insights":[199],"on":[200],"nature":[202],"hidden":[207],"relationships":[208],"between":[209],"classes.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2}],"updated_date":"2026-05-22T09:01:20.584952","created_date":"2025-10-10T00:00:00"}
